Cancer detection_for project.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7c8507dd",
   "metadata": {},
   "outputs": [],
   "source": [
    "#data handling\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "#data visualization\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "#preprocessing\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.preprocessing import label_binarize\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "#feature selection\n",
    "from sklearn.feature_selection import mutual_info_classif\n",
    "\n",
    "#classification\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "# performance metrics\n",
    "from sklearn.metrics import f1_score,precision_score, recall_score\n",
    "from sklearn.metrics import classification_report\n",
    "from sklearn.metrics import roc_curve,auc\n",
    "from sklearn.metrics import roc_auc_score\n",
    "# remember confusion matrices lets import that and execute it later"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d02d2ee3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gene_1</th>\n",
       "      <th>gene_2</th>\n",
       "      <th>gene_3</th>\n",
       "      <th>gene_4</th>\n",
       "      <th>gene_5</th>\n",
       "      <th>gene_6</th>\n",
       "      <th>gene_7</th>\n",
       "      <th>gene_8</th>\n",
       "      <th>gene_9</th>\n",
       "      <th>gene_10</th>\n",
       "      <th>...</th>\n",
       "      <th>gene_7992</th>\n",
       "      <th>gene_7993</th>\n",
       "      <th>gene_7994</th>\n",
       "      <th>gene_7995</th>\n",
       "      <th>gene_7996</th>\n",
       "      <th>gene_7997</th>\n",
       "      <th>gene_7998</th>\n",
       "      <th>gene_7999</th>\n",
       "      <th>gene_8000</th>\n",
       "      <th>Cancer_Type</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.088413</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.550605</td>\n",
       "      <td>2.815760</td>\n",
       "      <td>...</td>\n",
       "      <td>11.558803</td>\n",
       "      <td>8.881802</td>\n",
       "      <td>6.014840</td>\n",
       "      <td>6.643534</td>\n",
       "      <td>11.740624</td>\n",
       "      <td>7.065012</td>\n",
       "      <td>9.932659</td>\n",
       "      <td>6.928584</td>\n",
       "      <td>2.088413</td>\n",
       "      <td>KIRC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.205955</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.425244</td>\n",
       "      <td>2.354396</td>\n",
       "      <td>...</td>\n",
       "      <td>11.062829</td>\n",
       "      <td>9.032864</td>\n",
       "      <td>5.054193</td>\n",
       "      <td>6.432320</td>\n",
       "      <td>12.104985</td>\n",
       "      <td>7.300746</td>\n",
       "      <td>9.872796</td>\n",
       "      <td>5.039231</td>\n",
       "      <td>2.448002</td>\n",
       "      <td>KIRC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4.746646</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.639417</td>\n",
       "      <td>1.657091</td>\n",
       "      <td>...</td>\n",
       "      <td>12.497640</td>\n",
       "      <td>7.198160</td>\n",
       "      <td>0.943434</td>\n",
       "      <td>7.371690</td>\n",
       "      <td>11.202356</td>\n",
       "      <td>8.426588</td>\n",
       "      <td>11.176890</td>\n",
       "      <td>3.119738</td>\n",
       "      <td>4.433988</td>\n",
       "      <td>BRCA</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.173191</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.527371</td>\n",
       "      <td>2.732899</td>\n",
       "      <td>...</td>\n",
       "      <td>11.261713</td>\n",
       "      <td>8.725676</td>\n",
       "      <td>6.300418</td>\n",
       "      <td>6.036451</td>\n",
       "      <td>11.732303</td>\n",
       "      <td>7.559469</td>\n",
       "      <td>9.596453</td>\n",
       "      <td>2.863046</td>\n",
       "      <td>3.380342</td>\n",
       "      <td>KIRC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.366532</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.388355</td>\n",
       "      <td>...</td>\n",
       "      <td>12.241965</td>\n",
       "      <td>7.685204</td>\n",
       "      <td>5.142948</td>\n",
       "      <td>6.355788</td>\n",
       "      <td>11.493950</td>\n",
       "      <td>8.139444</td>\n",
       "      <td>10.189256</td>\n",
       "      <td>6.544487</td>\n",
       "      <td>0.839395</td>\n",
       "      <td>COAD</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 8001 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   gene_1  gene_2  gene_3    gene_4  gene_5  gene_6  gene_7  gene_8    gene_9  \\\n",
       "0     0.0     0.0     0.0  2.088413     0.0     0.0     0.0     0.0  0.550605   \n",
       "1     0.0     0.0     0.0  3.205955     0.0     0.0     0.0     0.0  0.425244   \n",
       "2     0.0     0.0     0.0  4.746646     0.0     0.0     0.0     0.0  2.639417   \n",
       "3     0.0     0.0     0.0  1.173191     0.0     0.0     0.0     0.0  1.527371   \n",
       "4     0.0     0.0     0.0  1.366532     0.0     0.0     0.0     0.0  0.000000   \n",
       "\n",
       "    gene_10  ...  gene_7992  gene_7993  gene_7994  gene_7995  gene_7996  \\\n",
       "0  2.815760  ...  11.558803   8.881802   6.014840   6.643534  11.740624   \n",
       "1  2.354396  ...  11.062829   9.032864   5.054193   6.432320  12.104985   \n",
       "2  1.657091  ...  12.497640   7.198160   0.943434   7.371690  11.202356   \n",
       "3  2.732899  ...  11.261713   8.725676   6.300418   6.036451  11.732303   \n",
       "4  3.388355  ...  12.241965   7.685204   5.142948   6.355788  11.493950   \n",
       "\n",
       "   gene_7997  gene_7998  gene_7999  gene_8000  Cancer_Type  \n",
       "0   7.065012   9.932659   6.928584   2.088413         KIRC  \n",
       "1   7.300746   9.872796   5.039231   2.448002         KIRC  \n",
       "2   8.426588  11.176890   3.119738   4.433988         BRCA  \n",
       "3   7.559469   9.596453   2.863046   3.380342         KIRC  \n",
       "4   8.139444  10.189256   6.544487   0.839395         COAD  \n",
       "\n",
       "[5 rows x 8001 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataframe = pd.read_csv(\"cancer_gene_expression.csv\")\n",
    "dataframe.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "1bd69c35",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 801 entries, 0 to 800\n",
      "Columns: 8001 entries, gene_1 to Cancer_Type\n",
      "dtypes: float64(8000), object(1)\n",
      "memory usage: 48.9+ MB\n"
     ]
    }
   ],
   "source": [
    "dataframe.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0c2d13fe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gene_1</th>\n",
       "      <th>gene_2</th>\n",
       "      <th>gene_3</th>\n",
       "      <th>gene_4</th>\n",
       "      <th>gene_5</th>\n",
       "      <th>gene_6</th>\n",
       "      <th>gene_7</th>\n",
       "      <th>gene_8</th>\n",
       "      <th>gene_9</th>\n",
       "      <th>gene_10</th>\n",
       "      <th>...</th>\n",
       "      <th>gene_7991</th>\n",
       "      <th>gene_7992</th>\n",
       "      <th>gene_7993</th>\n",
       "      <th>gene_7994</th>\n",
       "      <th>gene_7995</th>\n",
       "      <th>gene_7996</th>\n",
       "      <th>gene_7997</th>\n",
       "      <th>gene_7998</th>\n",
       "      <th>gene_7999</th>\n",
       "      <th>gene_8000</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.026642</td>\n",
       "      <td>0.231049</td>\n",
       "      <td>0.010844</td>\n",
       "      <td>2.405459</td>\n",
       "      <td>0.005799</td>\n",
       "      <td>0.065640</td>\n",
       "      <td>0.022036</td>\n",
       "      <td>0.028394</td>\n",
       "      <td>0.703998</td>\n",
       "      <td>1.916364</td>\n",
       "      <td>...</td>\n",
       "      <td>6.737536</td>\n",
       "      <td>11.606781</td>\n",
       "      <td>8.284388</td>\n",
       "      <td>5.056489</td>\n",
       "      <td>6.681599</td>\n",
       "      <td>11.567069</td>\n",
       "      <td>7.644004</td>\n",
       "      <td>10.299866</td>\n",
       "      <td>6.212981</td>\n",
       "      <td>2.418248</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.136850</td>\n",
       "      <td>0.656692</td>\n",
       "      <td>0.153859</td>\n",
       "      <td>0.797236</td>\n",
       "      <td>0.052265</td>\n",
       "      <td>0.213557</td>\n",
       "      <td>0.148917</td>\n",
       "      <td>0.161606</td>\n",
       "      <td>0.779321</td>\n",
       "      <td>0.877010</td>\n",
       "      <td>...</td>\n",
       "      <td>1.152086</td>\n",
       "      <td>0.536356</td>\n",
       "      <td>0.996495</td>\n",
       "      <td>1.907506</td>\n",
       "      <td>0.481615</td>\n",
       "      <td>0.332096</td>\n",
       "      <td>0.646763</td>\n",
       "      <td>0.443605</td>\n",
       "      <td>1.425559</td>\n",
       "      <td>1.510189</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2.711275</td>\n",
       "      <td>9.227476</td>\n",
       "      <td>4.256037</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>4.753610</td>\n",
       "      <td>10.245493</td>\n",
       "      <td>5.833191</td>\n",
       "      <td>8.850653</td>\n",
       "      <td>0.713256</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.898595</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.357214</td>\n",
       "      <td>...</td>\n",
       "      <td>5.990978</td>\n",
       "      <td>11.303079</td>\n",
       "      <td>7.741703</td>\n",
       "      <td>3.789875</td>\n",
       "      <td>6.410729</td>\n",
       "      <td>11.370420</td>\n",
       "      <td>7.247358</td>\n",
       "      <td>10.036599</td>\n",
       "      <td>5.388155</td>\n",
       "      <td>1.355524</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.358284</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.518031</td>\n",
       "      <td>1.877862</td>\n",
       "      <td>...</td>\n",
       "      <td>6.795390</td>\n",
       "      <td>11.561670</td>\n",
       "      <td>8.393605</td>\n",
       "      <td>5.137995</td>\n",
       "      <td>6.725305</td>\n",
       "      <td>11.579127</td>\n",
       "      <td>7.682742</td>\n",
       "      <td>10.260555</td>\n",
       "      <td>6.219147</td>\n",
       "      <td>2.266787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.929355</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.123931</td>\n",
       "      <td>2.486792</td>\n",
       "      <td>...</td>\n",
       "      <td>7.540330</td>\n",
       "      <td>11.854198</td>\n",
       "      <td>8.957813</td>\n",
       "      <td>6.458705</td>\n",
       "      <td>7.007823</td>\n",
       "      <td>11.765257</td>\n",
       "      <td>8.070051</td>\n",
       "      <td>10.515887</td>\n",
       "      <td>7.100357</td>\n",
       "      <td>3.238603</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.482332</td>\n",
       "      <td>6.575004</td>\n",
       "      <td>3.778061</td>\n",
       "      <td>4.746646</td>\n",
       "      <td>0.570754</td>\n",
       "      <td>1.866275</td>\n",
       "      <td>2.169925</td>\n",
       "      <td>2.375957</td>\n",
       "      <td>4.541670</td>\n",
       "      <td>4.932231</td>\n",
       "      <td>...</td>\n",
       "      <td>9.582974</td>\n",
       "      <td>14.146465</td>\n",
       "      <td>11.171433</td>\n",
       "      <td>10.590147</td>\n",
       "      <td>10.577240</td>\n",
       "      <td>12.730315</td>\n",
       "      <td>10.564759</td>\n",
       "      <td>13.031698</td>\n",
       "      <td>11.281391</td>\n",
       "      <td>9.738466</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 8000 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           gene_1      gene_2      gene_3      gene_4      gene_5      gene_6  \\\n",
       "count  801.000000  801.000000  801.000000  801.000000  801.000000  801.000000   \n",
       "mean     0.026642    0.231049    0.010844    2.405459    0.005799    0.065640   \n",
       "std      0.136850    0.656692    0.153859    0.797236    0.052265    0.213557   \n",
       "min      0.000000    0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "25%      0.000000    0.000000    0.000000    1.898595    0.000000    0.000000   \n",
       "50%      0.000000    0.000000    0.000000    2.358284    0.000000    0.000000   \n",
       "75%      0.000000    0.000000    0.000000    2.929355    0.000000    0.000000   \n",
       "max      1.482332    6.575004    3.778061    4.746646    0.570754    1.866275   \n",
       "\n",
       "           gene_7      gene_8      gene_9     gene_10  ...   gene_7991  \\\n",
       "count  801.000000  801.000000  801.000000  801.000000  ...  801.000000   \n",
       "mean     0.022036    0.028394    0.703998    1.916364  ...    6.737536   \n",
       "std      0.148917    0.161606    0.779321    0.877010  ...    1.152086   \n",
       "min      0.000000    0.000000    0.000000    0.000000  ...    2.711275   \n",
       "25%      0.000000    0.000000    0.000000    1.357214  ...    5.990978   \n",
       "50%      0.000000    0.000000    0.518031    1.877862  ...    6.795390   \n",
       "75%      0.000000    0.000000    1.123931    2.486792  ...    7.540330   \n",
       "max      2.169925    2.375957    4.541670    4.932231  ...    9.582974   \n",
       "\n",
       "        gene_7992   gene_7993   gene_7994   gene_7995   gene_7996   gene_7997  \\\n",
       "count  801.000000  801.000000  801.000000  801.000000  801.000000  801.000000   \n",
       "mean    11.606781    8.284388    5.056489    6.681599   11.567069    7.644004   \n",
       "std      0.536356    0.996495    1.907506    0.481615    0.332096    0.646763   \n",
       "min      9.227476    4.256037    0.000000    4.753610   10.245493    5.833191   \n",
       "25%     11.303079    7.741703    3.789875    6.410729   11.370420    7.247358   \n",
       "50%     11.561670    8.393605    5.137995    6.725305   11.579127    7.682742   \n",
       "75%     11.854198    8.957813    6.458705    7.007823   11.765257    8.070051   \n",
       "max     14.146465   11.171433   10.590147   10.577240   12.730315   10.564759   \n",
       "\n",
       "        gene_7998   gene_7999   gene_8000  \n",
       "count  801.000000  801.000000  801.000000  \n",
       "mean    10.299866    6.212981    2.418248  \n",
       "std      0.443605    1.425559    1.510189  \n",
       "min      8.850653    0.713256    0.000000  \n",
       "25%     10.036599    5.388155    1.355524  \n",
       "50%     10.260555    6.219147    2.266787  \n",
       "75%     10.515887    7.100357    3.238603  \n",
       "max     13.031698   11.281391    9.738466  \n",
       "\n",
       "[8 rows x 8000 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataframe.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1384f71c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(801, 8001)\n"
     ]
    }
   ],
   "source": [
    "#let's check the number of samples and features\n",
    "#note:the last column contain the labels. it is not considered as a feature\n",
    "\n",
    "print(dataframe.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "e20c8f4e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['gene_1', 'gene_2', 'gene_3', 'gene_4', 'gene_5', 'gene_6', 'gene_7',\n",
       "       'gene_8', 'gene_9', 'gene_10',\n",
       "       ...\n",
       "       'gene_7992', 'gene_7993', 'gene_7994', 'gene_7995', 'gene_7996',\n",
       "       'gene_7997', 'gene_7998', 'gene_7999', 'gene_8000', 'Cancer_Type'],\n",
       "      dtype='object', length=8001)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataframe.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "51209930",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "columns with missing values:0\n"
     ]
    }
   ],
   "source": [
    "#check for missing values\n",
    "datanul=dataframe.isnull().sum()\n",
    "g=[i for i in datanul if i>0]\n",
    "\n",
    "print('columns with missing values:%d'%len(g))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2c556f2c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BRCA    300\n",
      "KIRC    146\n",
      "LUAD    141\n",
      "PRAD    136\n",
      "COAD     78\n",
      "Name: Cancer_Type, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(dataframe['Cancer_Type'].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "a1d6794d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#plot a bar chat to display the class distribution\n",
    "\n",
    "dataframe['Cancer_Type'].value_counts().plot.bar()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "13a5334e",
   "metadata": {},
   "outputs": [],
   "source": [
    "#we will now seperate the feature values from the class. we do this because scikit-learn requires that features and class are separated before parsing them to the classifiers.\n",
    "\n",
    "X=dataframe.iloc[:,0:-1]\n",
    "y=dataframe.iloc[:,-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ebbf3e7e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   gene_1  gene_2  gene_3    gene_4  gene_5  gene_6  gene_7  gene_8    gene_9  \\\n",
      "0     0.0     0.0     0.0  2.088413     0.0     0.0     0.0     0.0  0.550605   \n",
      "1     0.0     0.0     0.0  3.205955     0.0     0.0     0.0     0.0  0.425244   \n",
      "2     0.0     0.0     0.0  4.746646     0.0     0.0     0.0     0.0  2.639417   \n",
      "3     0.0     0.0     0.0  1.173191     0.0     0.0     0.0     0.0  1.527371   \n",
      "4     0.0     0.0     0.0  1.366532     0.0     0.0     0.0     0.0  0.000000   \n",
      "\n",
      "    gene_10  ...  gene_7991  gene_7992  gene_7993  gene_7994  gene_7995  \\\n",
      "0  2.815760  ...   6.883022  11.558803   8.881802   6.014840   6.643534   \n",
      "1  2.354396  ...   6.271456  11.062829   9.032864   5.054193   6.432320   \n",
      "2  1.657091  ...   8.417734  12.497640   7.198160   0.943434   7.371690   \n",
      "3  2.732899  ...   4.767210  11.261713   8.725676   6.300418   6.036451   \n",
      "4  3.388355  ...   7.594086  12.241965   7.685204   5.142948   6.355788   \n",
      "\n",
      "   gene_7996  gene_7997  gene_7998  gene_7999  gene_8000  \n",
      "0  11.740624   7.065012   9.932659   6.928584   2.088413  \n",
      "1  12.104985   7.300746   9.872796   5.039231   2.448002  \n",
      "2  11.202356   8.426588  11.176890   3.119738   4.433988  \n",
      "3  11.732303   7.559469   9.596453   2.863046   3.380342  \n",
      "4  11.493950   8.139444  10.189256   6.544487   0.839395  \n",
      "\n",
      "[5 rows x 8000 columns]\n"
     ]
    }
   ],
   "source": [
    "print(X.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f1f32189",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(801, 8000)"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "179c602e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    KIRC\n",
      "1    KIRC\n",
      "2    BRCA\n",
      "3    KIRC\n",
      "4    COAD\n",
      "Name: Cancer_Type, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(y.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "7cb925ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(801,)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "7cdb437d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#let's encode target labels (y) with values between 0 and n_classes-1.\n",
    "#encoding will be done using the LabelEncoder\n",
    "label_encoder=LabelEncoder()\n",
    "label_encoder.fit(y)\n",
    "y_encoded=label_encoder.transform(y)\n",
    "labels=label_encoder.classes_\n",
    "classes=np.unique(y_encoded)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "a58a4689",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['BRCA', 'COAD', 'KIRC', 'LUAD', 'PRAD'], dtype=object)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "5576b768",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 2, 3, 4])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "03958ef2",
   "metadata": {},
   "outputs": [],
   "source": [
    "#split data into training and test sets\n",
    "X_train,X_test,y_train,y_test=train_test_split(X,y_encoded,test_size=0.2,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "a827ed98",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>gene_1</th>\n",
       "      <th>gene_2</th>\n",
       "      <th>gene_3</th>\n",
       "      <th>gene_4</th>\n",
       "      <th>gene_5</th>\n",
       "      <th>gene_6</th>\n",
       "      <th>gene_7</th>\n",
       "      <th>gene_8</th>\n",
       "      <th>gene_9</th>\n",
       "      <th>gene_10</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "      <td>801.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.026642</td>\n",
       "      <td>0.231049</td>\n",
       "      <td>0.010844</td>\n",
       "      <td>2.405459</td>\n",
       "      <td>0.005799</td>\n",
       "      <td>0.065640</td>\n",
       "      <td>0.022036</td>\n",
       "      <td>0.028394</td>\n",
       "      <td>0.703998</td>\n",
       "      <td>1.916364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.136850</td>\n",
       "      <td>0.656692</td>\n",
       "      <td>0.153859</td>\n",
       "      <td>0.797236</td>\n",
       "      <td>0.052265</td>\n",
       "      <td>0.213557</td>\n",
       "      <td>0.148917</td>\n",
       "      <td>0.161606</td>\n",
       "      <td>0.779321</td>\n",
       "      <td>0.877010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.898595</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.357214</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.358284</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.518031</td>\n",
       "      <td>1.877862</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.929355</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.123931</td>\n",
       "      <td>2.486792</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.482332</td>\n",
       "      <td>6.575004</td>\n",
       "      <td>3.778061</td>\n",
       "      <td>4.746646</td>\n",
       "      <td>0.570754</td>\n",
       "      <td>1.866275</td>\n",
       "      <td>2.169925</td>\n",
       "      <td>2.375957</td>\n",
       "      <td>4.541670</td>\n",
       "      <td>4.932231</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           gene_1      gene_2      gene_3      gene_4      gene_5      gene_6  \\\n",
       "count  801.000000  801.000000  801.000000  801.000000  801.000000  801.000000   \n",
       "mean     0.026642    0.231049    0.010844    2.405459    0.005799    0.065640   \n",
       "std      0.136850    0.656692    0.153859    0.797236    0.052265    0.213557   \n",
       "min      0.000000    0.000000    0.000000    0.000000    0.000000    0.000000   \n",
       "25%      0.000000    0.000000    0.000000    1.898595    0.000000    0.000000   \n",
       "50%      0.000000    0.000000    0.000000    2.358284    0.000000    0.000000   \n",
       "75%      0.000000    0.000000    0.000000    2.929355    0.000000    0.000000   \n",
       "max      1.482332    6.575004    3.778061    4.746646    0.570754    1.866275   \n",
       "\n",
       "           gene_7      gene_8      gene_9     gene_10  \n",
       "count  801.000000  801.000000  801.000000  801.000000  \n",
       "mean     0.022036    0.028394    0.703998    1.916364  \n",
       "std      0.148917    0.161606    0.779321    0.877010  \n",
       "min      0.000000    0.000000    0.000000    0.000000  \n",
       "25%      0.000000    0.000000    0.000000    1.357214  \n",
       "50%      0.000000    0.000000    0.518031    1.877862  \n",
       "75%      0.000000    0.000000    1.123931    2.486792  \n",
       "max      2.169925    2.375957    4.541670    4.932231  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataframe.iloc[:,0:10].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "53fbb41a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# scale data between 0 and 1\n",
    "\n",
    "min_max_scaler=MinMaxScaler()\n",
    "X_train_norm=min_max_scaler.fit_transform(X_train)\n",
    "X_test_norm=min_max_scaler.fit_transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "5328819a",
   "metadata": {},
   "outputs": [],
   "source": [
    "MI=mutual_info_classif(X_train_norm,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "3b2fb0ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "#select top n features. lets say 300.\n",
    "#you can modify the value and see how the performance of the model changes\n",
    "\n",
    "n_features=300\n",
    "selected_scores_indices=np.argsort(MI)[::-1][0:n_features]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "b706cc3a",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_selected=X_train_norm[:,selected_scores_indices]\n",
    "X_test_selected=X_test_norm[:,selected_scores_indices]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "b8f58f9e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(640, 300)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_selected.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "d3b4772e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(161, 300)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test_selected.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "9191e80f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Random Forest Classifier\n",
    "#because we are dealing with multiclass data, the one versus rest strategy is used.\n",
    "#learn to predict each class against the other.\n",
    "\n",
    "RF=OneVsRestClassifier(RandomForestClassifier(max_features=0.2))\n",
    "RF.fit(X_train_selected,y_train)\n",
    "y_pred =RF.predict(X_test_selected)\n",
    "pred_prob = RF.predict_proba(X_test_selected)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "1faaae72",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "precision:0.9758\n",
      "recall:0.9752\n",
      "f1score:0.9748\n",
      "\n",
      "\n",
      "classification report\n",
      "\n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "        BRCA       0.95      1.00      0.98        60\n",
      "        COAD       1.00      0.88      0.93        16\n",
      "        KIRC       1.00      1.00      1.00        28\n",
      "        LUAD       0.96      0.92      0.94        24\n",
      "        PRAD       1.00      1.00      1.00        33\n",
      "\n",
      "    accuracy                           0.98       161\n",
      "   macro avg       0.98      0.96      0.97       161\n",
      "weighted avg       0.98      0.98      0.97       161\n",
      "\n"
     ]
    }
   ],
   "source": [
    "#accuracy\n",
    "#accuracy=np.round(balanced_accuracy_score(y_test,y_pred),4)\n",
    "#print('accuracy:%0.4f'%accuracy)\n",
    "\n",
    "#precision\n",
    "precision=np.round(precision_score(y_test,y_pred,average = 'weighted'),4)\n",
    "print('precision:%0.4f'%precision)\n",
    "\n",
    "#recall\n",
    "recall=np.round(recall_score(y_test,y_pred,average = 'weighted'),4)\n",
    "print('recall:%0.4f'%recall)\n",
    "\n",
    "#f1score\n",
    "f1score=np.round(f1_score(y_test,y_pred,average = 'weighted'),4)\n",
    "print('f1score:%0.4f'%f1score)\n",
    "\n",
    "\n",
    "report=classification_report(y_test,y_pred, target_names=labels)\n",
    "print('\\n')\n",
    "print('classification report\\n\\n')\n",
    "print(report)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "79ee372e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "cm_df=confusion_matrix(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "afa58078",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[60,  0,  0,  0,  0],\n",
       "       [ 1, 14,  0,  1,  0],\n",
       "       [ 0,  0, 28,  0,  0],\n",
       "       [ 2,  0,  0, 22,  0],\n",
       "       [ 0,  0,  0,  0, 33]], dtype=int64)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cm_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "8a8cbb14",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(50.722222222222214, 0.5, 'True Labels')"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#visualize the confusion matrix using seaborn\n",
    "\n",
    "sns.heatmap(cm_df,annot=True,cmap='Blues')\n",
    "plt.xlabel('Predicted Labels')\n",
    "plt.ylabel('True Labels')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2961f160",
   "metadata": {},
   "outputs": [],
   "source": [
    "by nischal."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}